/** Pattern for extracting charset from meta tags. */
    protected Pattern metaCharsetPattern = Pattern.compile("<meta.*content\\s*=\\s*['\"].*;\\s*charset=([\\w\\d\\-_]*)['\"]\\s*/?>",
            Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    /**
     * Pattern for HTML tags.
     */
    protected Pattern htmlTagPattern = Pattern.compile("<[^>]+>");

    /** Map of parser features. */

                        return getList(OpenSearchUrlFilter.class, key, QueryBuilders.termQuery(FILTER_TYPE, type), null, maxLoadSize, null)
                                .stream()
                                .map(f -> Pattern.compile(f.getUrl()))
                                .collect(Collectors.toList());
                    }
                });
    }

    /**
     * Adds an include URL filter for the specified session.
     *

     * @param key the field name to match against
     * @param regex the regular expression pattern
     */
    public void addRule(final String key, final String regex) {
        regexMap.put(key, Pattern.compile(regex));
    }

    /**
     * Adds a compiled regular expression rule for the specified field.
     * @param key the field name to match against
     * @param pattern the compiled regular expression pattern

        }
        final Matcher matcher = getTagPattern().matcher(input);
        final StringBuffer sb = new StringBuffer();
        final Pattern attrPattern = Pattern.compile("\\s[^ ]+=\"([^\"]*)\"");
        while (matcher.find()) {
            final String tagStr = matcher.group();
            final Matcher attrMatcher = attrPattern.matcher(tagStr);

     *
     * @param directive The directive to add to the robots.txt rules
     */
    public void addDirective(final Directive directive) {
        directiveMap.put(Pattern.compile(directive.getUserAgent().replace("*", ".*"), Pattern.CASE_INSENSITIVE), directive);
    }

    /**
     * Adds a sitemap URL to the list of sitemaps.
     *
     * @param url The URL of the sitemap to be added

     * If you want to follow a html spec, use 512. */
    protected int preloadSizeForCharset = 2048;

    /**
     * Pattern for invalid URLs.
     */
    protected Pattern invalidUrlPattern = Pattern.compile("^\\s*javascript:|" //
            + "^\\s*mailto:|" //
            + "^\\s*irc:|" //
            + "^\\s*skype:|" //
            + "^\\s*about:|" + "^\\s*fscommand:|" //
            + "^\\s*aim:|" //

     * Example: <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     */
    protected Pattern metaCharsetPattern = Pattern.compile("<meta.*content\\s*=\\s*['\"].*;\\s*charset=([\\w\\d\\-_]*)['\"]\\s*/?>",
            Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    /**
     * Map of features for the DOM parser.
     */

     * @param content The content to search.
     * @return The extracted token value.
     */
    protected String getTokenValue(final String tokenPattern, final String content) {
        final Matcher matcher = Pattern.compile(tokenPattern).matcher(content);
        if (matcher.find()) {
            if (logger.isDebugEnabled()) {
                logger.debug("Matched: {}", matcher.group());
            }

     */
    public XpathTransformer() {
        super();
    }

    private static final Logger logger = LogManager.getLogger(XpathTransformer.class);

    private static final Pattern SPACE_PATTERN = Pattern.compile("\\s+", Pattern.MULTILINE);

    /**
     * A map of field rules, where the key is the field name and the value is the XPath expression.
     */
    protected Map<String, String> fieldRuleMap = new LinkedHashMap<>();

 * </pre>
 */
public class XmlTransformer extends AbstractTransformer {
    private static final Logger logger = LogManager.getLogger(XmlTransformer.class);

    private static final Pattern SPACE_PATTERN = Pattern.compile("\\s+", Pattern.MULTILINE);

    /**
     * If true, the parser will be namespace aware.
     */
    protected boolean namespaceAware;

    /**